INDEX

Explanations

references to specific individuals or entities, particularly those related to legal or academic contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Strings starting with "Nam", "Nim", or "NM"

np_acts-logits-general · gemini-2.0-flash

N-vowel-m and N-words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autour

-0.39

ambién

-0.38

Elaboración

-0.37

 natten

-0.36

corazón

-0.36

consejos

-0.36

 acogedor

-0.36

丁寧

-0.36

 strani

-0.35

 compris

-0.33

POSITIVE LOGITS

parsedMessage

0.67

 EconPapers

0.66

 AssemblyCulture

0.64

TagMode

0.62

 Signalez

0.59

出版年

0.57

 Roskov

0.56

 Nomin

0.51

 Numerade

0.51

ConstraintMaker

0.50

Activations Density 0.136%

references to specific individuals or entities, particularly those related to legal or academic contexts

Strings starting with "Nam", "Nim", or "NM"

N-vowel-m and N-words

No Comments

No Known Activations

references to specific individuals or entities, particularly those related to legal or academic contexts

Strings starting with "Nam", "Nim", or "NM"

N-vowel-m and N-words

No Comments

No Known Activations